Lifelong and Interactive Learning of Factual Knowledge in Dialogues

Mazumder, Sahisnu; Liu, Bing; Wang, Shuai; Ma, Nianzu

doi:10.18653/v1/w19-5903

Cited by 22 publications

(16 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Closer to our work, is the self-feeding chatbot (Hancock et al, 2019), where dialogue models were used to collect data to improve themselves via crowdsourcing utilizing the PersonaChat task. Related approaches have also been applied to the cases of question answering (Li et al, 2016a,b), and in simulators (Mazumder et al, 2019;Nguyen and Daumé III, 2019) as well. applied such an approach to goal-oriented tasks.…”

Section: Related Workmentioning

confidence: 99%

Dialogue in the Wild: Learning from a Deployed Role-Playing Game with Humans and Bots

Shuster¹,

Urbanek²,

Dinan³

et al. 2021

Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

View full text Add to dashboard Cite

Much of NLP research has focused on crowdsourced static datasets and the supervised learning paradigm of training once and then evaluating test performance. As argued in de Vries et al. (2020), crowdsourced data has the issues of lack of naturalness and relevance to real-world use cases, while the static dataset paradigm does not allow for a model to learn from its experiences of using language (Silver et al., 2013). In contrast, one might hope for machine learning systems that become more useful as they interact with people. In this work, we build and deploy a role-playing game, whereby human players converse with learning agents situated in an open-domain fantasy world. We show that by training models on the conversations they have with humans in the game the models progressively improve, as measured by automatic metrics and online engagement scores. This learning is shown to be more efficient than crowdsourced data when applied to conversations with real users, as well as being far cheaper to collect.

show abstract

Section: Related Workmentioning

confidence: 99%

Dialogue in the Wild: Learning from a Deployed Role-Playing Game with Humans and Bots

Shuster¹,

Urbanek²,

Dinan³

et al. 2021

Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

View full text Add to dashboard Cite

show abstract

“…Mazumder et al [29] proposed a method for acquiring knowledge through dialogues based on a knowledge graph. When the dialogue system cannot reply to a user question based only on the knowledge graph, it asks the user to add information related to the question and stores the knowledge extracted from the user's answer.…”

Section: Knowledge Acquisition In Dialogue Systemsmentioning

confidence: 99%

Knowledge Graph Completion-based Question Selection for Acquiring Domain Knowledge through Dialogues

Komatani

Fujioka

Nakashima

et al. 2021

26th International Conference on Intelligent User Interfaces

View full text Add to dashboard Cite

Building a perfect knowledge base in a certain domain is practically impossible, so it is effective for dialogue systems to acquire knowledge for enhancing an imperfect knowledge base through natural language dialogues with users. This paper proposes a framework for selecting questions for such knowledge acquisition when a knowledge graph is used as the knowledge base. The framework uses knowledge graph completion (KGC) for predicting new links that are likely to be correct and selects questions on the basis of the KGC scores. One of the problems with this framework is that questions with incorrect content might be selected, which often occurs when the link prediction performance is low, and this would reduce the users' willingness to engage in dialogues. To alleviate this problem, this paper presents two modifications to the KGC training: 1) creating pseudo entities having substrings of the names of the entities in the graph so that the entities whose names share substrings are connected and 2) limiting the range of negative sampling. Cross validation-based experiments we conducted showed that these modifications improved KGC performance. We also conducted a user study with crowdsourcing to investigate the subjective perception of the correctness of the predicted links. The results suggest that the model trained with the modifications is capable of avoiding questions with incorrect content. CCS CONCEPTS• Computing methodologies → Discourse, dialogue and pragmatics.

show abstract

“…The chatbot can easily answer yes. Ask when it does not understand something: Mazumder et al (2019a) proposed a method to do this in the context of building natural language interfaces (NLI). One of the key issues is how to understand paraphrased natural language (NL) commands from users in order to map a user command to a system's API call.…”

Section: On-the-job Learning During Conversationsmentioning

confidence: 99%

Learning on the Job: Online Lifelong and Continual Learning

Liu

2020

AAAI

Self Cite

View full text Add to dashboard Cite

One of the hallmarks of the human intelligence is the ability to learn continuously, accumulate the knowledge learned in the past and use the knowledge to help learn more and learn better. It is hard to imagine a truly intelligent system without this capability. This type of learning differs significantly than the classic machine learning (ML) paradigm of isolated single-task learning. Although there is already research on learning a sequence of tasks incrementally under the names of lifelong learning or continual learning, they still follow the traditional two-phase separate training and testing paradigm in learning each task. The tasks are also given by the user. This paper adds on-the-job learning to the mix to emphasize the need to learn during application (thus online) after the model has been deployed, which traditional ML cannot do. It aims to leverage the learned knowledge to discover new tasks, interact with humans and the environment, make inferences, and incrementally learn the new tasks on the fly during applications in a self-supervised and interactive manner. This is analogous to human on-the-job learning after formal training. We use chatbots and self-driving cars as examples to discuss the need, some initial work, and key challenges and opportunities in building this capability.

show abstract

Lifelong and Interactive Learning of Factual Knowledge in Dialogues

Cited by 22 publications

References 38 publications

Dialogue in the Wild: Learning from a Deployed Role-Playing Game with Humans and Bots

Dialogue in the Wild: Learning from a Deployed Role-Playing Game with Humans and Bots

Knowledge Graph Completion-based Question Selection for Acquiring Domain Knowledge through Dialogues

Learning on the Job: Online Lifelong and Continual Learning

Contact Info

Product

Resources

About